Description:FIELD OF INVENTION
[001] The present invention relates to a system and method for context based advertising in physical spaces. Particularly, the present invention relates to a system and method for real-time target advertisements based on the context of the keywords spoken by users in vicinity.
BACKGROUND OF THE INVENTION
[002] Conventionally, various out-of-home advertising is used to gain consumers’ attention or marketing advertisements when they are “on the go” in public places, in transit, waiting (such as in a medical office), and/or in specific commercial locations. The out-of-home advertising are static advertisements that are used in physical spaces public places, malls, shops, retail outlets, supermarkets, and the like as well as in a kiosk, standee, digital screen etc. It also includes place-based media seen in places such as convenience stores, medical centers, salons, and other brick-and-mortar venues. However, contextual advertising is a modern game changer to modern advertising. The ads in contextual advertising works by placing advertisements on relevant websites designed to target relevant audiences where the advertising is done by analyzing relevant keywords and content on the web page itself, including user browsing behavior.

[003] Approximately four out of 100 ads per day gain more than one second of attention, and to stand any chance of being one of them, marketing brands need to introduce personalization of ads as well as making the advertising completely relevant and personal to the viewer, especially at the time when it is presented. The maximum impact of the advertisement and probability of its achieving its purpose is when it is presented to users when they are actually looking for the particular product or service. In the present scenario, static advertisements work on demographic data or past user behavior, due to which it limits the scalability of the advertisement. Traditional static advertisements often suffer from a lack of relevance and dynamic nature, as they are not able to target advertisements based on the context or growing requirement of the users. This can further lead to low engagement rates and low conversion rates for businesses, as users are less likely to interact with advertisements that are not relevant to their needs or interests.

[004] Additionally, the traditional static advertisements are often expensive and time-consuming to update, and require manual intervention for even small changes. This may result in an outdated or irrelevant advertisements being displayed, reducing the effectiveness of the advertising and wasting resources for businesses.

[005] In view of the above problems associated with the state of art, there is a need to develop a system and method for context based advertising in physical spaces, providing a real-time and context-based flexible, adaptable, and scalable advertising solutions.

OBJECTIVES OF THE INVENTION
[006] The primary objective of the present invention is to provide a system and method for context based advertising in physical spaces.

[007] Another objective of the present invention is to integrate speech recognition, Natural Language processing, and Machine learning technology with Internet of Things (IoT) devices to provide real-time and context-based advertising in physical spaces.

[008] Yet another objective of the present invention is to provide contextual advertisements that can respond to the changing context of users in real-time.

[009] Yet another objective of the present invention is to provide a scalable and cost-effective solution for businesses of all sizes and types, while offering a more relevant and dynamic advertising experience for users.

[0010] Other objects and advantages of the present invention will become apparent from the following description taken in connection with the accompanying drawings, wherein, by way of illustration and example, the aspects of the present invention are disclosed.

SUMMARY OF THE INVENTION

[0011] The present invention relates to a system and method for context based advertising in physical spaces. Particularly, the present invention relates to a system and method for real-time target advertisements based on the context of the keywords spoken by users in vicinity. The system for providing context-based advertisements in physical spaces comprises the following components: a plurality of Internet of Things (IoT) devices configured in a plurality of physical spaces; a microphone array installed in the IoT devices to capture speech inputs of people in vicinity; a processing unit wiredly/wirelessly connected to the microphone array to receive speech inputs; a storage unit wiredly/wirelessly connected to the IoT devices to store a plurality of keywords related to advertisements, and pre-set video data based on keywords; and an output module wiredly/wirelessly connected to the processing unit. The processing unit analyzes and identifies a plurality of keywords received from the microphone array, so as to compare identified keywords with pre-set video data and/ or keywords fed into the software module to trigger playback of advertisement related to keywords through an output module.

BRIEF DESCRIPTION OF DRAWINGS
[0012] An understanding of the present invention may be obtained by reference to the accompanying drawings, when taken in conjunction with the description herein and in which:

[0013] Figure 1 illustrates one particular architecture for context based advertising in physical spaces;

[0014] Figure 2 illustrates detailed overview of each component of the smart IoT devices for contextual ads on physical spaces in manual mode.

[0015] Figure 3 illustrates detailed overview of each component of the smart IoT devices for contextual ads on physical spaces in manual mode.

DETAILED DESCRIPTION OF THE INVENTION
[0016] The following description describes various features and functions of the disclosed system with reference to the accompanying figures. In the figures, similar symbols identify similar components, unless context dictates otherwise. The illustrative aspects described herein are not meant to be limiting. It may be readily understood that certain aspects of the disclosed system can be arranged and combined in a wide variety of different configurations, all of which have not been contemplated herein.

[0017] Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0018] Features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.

[0019] The terms and words used in the following description are not limited to the bibliographical meanings, but, are merely used to enable a clear and consistent understanding of the invention. Accordingly, it should be apparent to those skilled in the art that the following description of exemplary embodiments of the present invention are provided for illustrative purpose only and not for the purpose of limiting the invention.

[0020] It is to be understood that the singular forms “a”, “an” and “the” include plural referents unless the context clearly dictates otherwise.

[0021] It should be emphasized that the term “comprises/comprising” when used in this specification is taken to specify the presence of stated features, integers, steps or components but does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof.

[0022] The present invention relates to a system and method for context based advertising in physical spaces. Particularly, the present invention relates to a system and method for real-time target advertisements based on the context of the keywords spoken by users in vicinity.

[0023] The system of the present invention includes the integration of Internet-of-Things (IoT) with speech recognition technology, NLP and Machine learning technology to provide context based advertising in physical spaces. The IoT based system for context based advertising in physical spaces operates on the basis of context of keywords spoken by users in vicinity. The contextual advertising enables higher level of accuracy and relevance in advertising in physical spaces, resulting in improved engagement and higher conversion rates. The ads in contextual advertisements are configured to respond depending on the changing context of users in real-time.

[0024] In an embodiment of the present invention, Figure 1 illustrates one particular architecture for context based advertising in physical spaces. The concept of contextual ads on physical spaces involves the use of smart IoT devices that are strategically placed or installed in various physical locations. These devices are designed to understand the voices of people or consumers who are within the vicinity and are discussing topics related to the products or services being advertised. The smart IoT devices captures specific keywords related to the advertisement so as to process the keywords and play real-time ads via audio and/ or video modalities. The system ensures to provide targeted advertisement related to the consumers interest by receiving and processing the keywords of the consumers within the vicinity of the IoT devices.

[0025] The system for providing context-based advertisements in physical spaces comprises: a plurality of Internet of Things (IoT) devices; a microphone array installed in the IoT devices to capture speech input from people in vicinity; a processing unit for analyzing the data captured by microphone array and initiating the playback of relevant ads based on pre-set of video data fed into a storage unit; the storage unit is wirelessly/ wiredly connected to the IoT devices; and an output module wiredly/ wirelessly connected to the IoT devices for playing the ads via audio and/ or video modalities. The IoT devices of the system are further integrated with automatic speech recognition module, natural language processing module and machine learning module to enable the system to provide context based advertisement automatically. Alternatively, the system can also operate manually by connecting a communication unit of the user with the nearby IoT device to send real-time data of ads played analytics and control the device remotely.

[0026] In a preferred embodiment, a system for context-based advertisements is operated by integrating: a plurality of Internet of Things (IoT) devices; a plurality of speech- recognition module, NLP module and ML module configured in at least one IoT device for receiving speech inputs from a plurality of users in vicinity of the IoT devices, so as to recognize key words from the speech input.

[0027] The system is configured to be operated in any one of the two mode: automatic mode; or manual mode, comprising the following components:
• Microphone Array: The microphone array is a set of microphones placed strategically on the IoT device to capture voices of people within its range. These microphones work together to provide a clear and accurate recording of the surrounding sounds and voices.
• Processing Unit: In an embodiment, a processing unit is configured for analyzing the captured data and initiating the playback of relevant ads via an output module such as, but not limited to, audio and video modality. The central server module further uses algorithms and machine learning technology to identify the keywords related to the advertisement and trigger the playback of ads through the output module.
• Storage Unit: In an embodiment, the storage unit is used to store the ads, such as but not limited to a pre-set video data and data for keyword matching. The storage module is pre-fed with a video data that allows advertisers to quickly and easily change the ads or keywords and deliver targeted advertisements to consumers in real-time. The storage unit can anytime be remotely accessed and updated using the communication unit.
• Speech transmission means/ Communication Unit: The communication unit allows the device to communicate with the outside world. It can be connected to Wi-Fi or LTE networks to send real-time data of ads played analytics and control the device remotely. The communication unit also allows advertisers to update ads and keywords remotely by connecting with the servers. In an alternate embodiment, the system is operated in a manual mode by physically accessing the IoT device through the communication unit to manually configure the IoT device for real-time advertisement. In such case, the advertisers need to manually configure the device by accessing the IoT device directly.
• ASR Module: In an embodiment, an Automatic Speech Recognition (ASR) module is used in manual mode. The ASR is configured to convert the recorded audio data from the user within vicinity into text data. The ASR module uses advanced algorithms to accurately transcribe the recorded audio into text data.
• NLP Module: The Natural Language Processing (NLP) module is used in manual mode. The NLP module is configured for analyzing the transcribed text data and identifying the keywords related to the advertisement. The NLP module uses advanced algorithms to understand the context of the conversation and identify the relevant keywords.
• ML Module: The Machine Learning (ML) module is responsible for analyzing the identified keywords and triggering the playback of relevant ads. This engine uses advanced machine learning technology to identify patterns in the data and make accurate predictions about which advertisement is need to be played.
• Output Module: The output module is configured for playing the ads via audio and/ or video modalities. The output module uses advanced audio and video processing algorithms to deliver high-quality audio and video playback to consumers via a display unit and/ or speakers respectively. In an exemplary embodiment, the IoT devices come with a built-in speaker and video output through which any HDMI screen/display can be connected to the output module.

[0028] In an embodiment, Figure 2 illustrates detailed overview of each component of the smart IoT devices for contextual ads on physical spaces in manual mode. the system is operated in a manual mode by pre-feeding all the relevant and necessary keywords and media files at the storage module through edge computing. The IoT devices are installed with microphone arrays to understand the speech input of users or consumers who are within the vicinity to recognize keywords of the discussing topics related to the products or services being advertised. Further, the speech input captured by microphone array are analyzed by ASR module to convert the recorded audio data into text data. The processing unit is configured a plurality of algorithms along with NLP module and ML module. The processing unit through NLP and ML module identifies the keywords and initiate the playback of relevant advertisement by matching the keywords with the pre-set video data fed into the storage module.

[0029] In an embodiment, the NLP module receives the text data from the ASR module and identifies the relevant keywords related to advertisements, and transmits the keywords to the ML module. The ML module analyzes the identified keywords and trigger the playback on the output module by matching the keywords with the pre-set video data
.
[0030] The integration of microphone arrays and IoT devices provides a real-time and context-based advertising solution, as advertisements are targeted based on the keywords spoken by users in the vicinity.

[0031] In an alternate embodiment, Figure 3 illustrates detailed overview of each component of the smart IoT devices for contextual ads on physical spaces in automatic mode. the system is operated in an automatic mode by further employing speech transmission means or a communication unit. The speech transmission means / communication means transmits the captured speech input from the microphone array to a central server module via a network. The speech transmission means/ communication unit is connected to the IoT device via a network means. As per this embodiment, the processing unit is configured to analyze speech inputs and identify keywords related to advertisements. Further, the identified keywords are transmitted to the central server module through the speech transmission means/ communication unit. The central server module processes the identified keywords and compare the identified keywords with the keywords of the pre-set data to obtain a matching advertisement in real-time. The central server module selects the advertisements based on the matching keyword from a data set of the advertisements stored in the storage module and updated new advertisements and/ or new keywords in the central server module. The central server module further transmits the selected advertisement to the output module of the IoT device, so as to trigger playback of advertisement related to keywords through an output module.

[0032] The storage module of advertisements and keywords are configured to be regularly updated to reflect changing business needs and to ensure that the system is delivering the best results possible.

[0033] In an exemplary embodiment, the automatic mode is operated by connecting the central server module with the IoT devices, where the central server module can be selected from: a software; or a hardware; or a combination of both, providing a scalable and adaptable solution for businesses of all sizes and types. The central sever allows easy updating of advertisements and keywords, ensuring that advertisements remain relevant and up-to-date. However, in manual mode, a set of advertisements, relevant to the local region, can be added onto the device and programmed to play on certain prompts by the advertisers.

[0034] In another embodiment, while making the system work in automatic mode, it is to be ensured that the IoT devices are positioned and configured in physical spaces within a network range to accurately listen and recognize keywords spoken by the user. The central server module to process keywords and select advertisements in real-time. The system provides regular ads and keywords updates to the storage module of the central server module, which ensures that the system continues to deliver the best results possible.

[0035] In an embodiment, the plurality of IoT devices of the system are installed in physical spaces such as public places, malls, shops, retail outlets, supermarket, kiosk, standee, digital screen, etc. The IoT devices installed in physical spaces are equipped with microphone arrays. The microphone arrays are configured to listen and recognize keywords spoken (in a multitude of languages and accents) by users in the vicinity. The keywords recognized by the processing unit are transmitted to a central server module via the speech transmission means. The processing unit identifies the key words and transmits recognized keywords to central server module for analyzing and selecting an advertisement based on the context of keywords. The selected advertisement is further transmitted to an output module configured in at least one IoT device for displaying the selected advertisements. In an exemplary embodiment, all the data analytics of advertisement played at various physical location gets real-time reflected to the web dashboard of the stakeholders.

[0036] In another embodiment, the IoT devices are configured to be placed in strategic locations where they can easily listen to and recognize accurate keywords spoken by users via the microphone arrays, even in noisy environments.

[0037] A method of providing context-based advertisements in physical spaces, comprising:
a. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
b. transmitting speech input captured by the microphone array to the processing unit of the IoT device;
c. analyzing speech inputs and identifying keywords related to advertisements by the processing unit;
d. triggering playback of advertisement related to keywords through an output module;
e. playing the advertisement on at least one output module configured on the IoT device.

[0038] In an embodiment, the method for providing context-based advertisements in manual mode, comprises the following:
a. pre-feeding keywords and media files related to advertisements at the storage module through edge computing;
b. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
c. transmitting speech input from the microphone array to an automatic search recognition module (ASR);
d. converting the recorded speech input/ audio data into text data via the ASR module;
e. transmitting text data to the processing unit configured with a natural language processing (NLP) module and a machine learning (ML) module;
f. analyzing text data through the NLP module to identify keywords related to advertisements;
g. analyzing keywords through the ML module by comparing identified keywords from the keywords of the pre-set video data fed into the storage module to trigger playback of relevant advertisement;
h. triggering playback of advertisement related to keywords through an output module;
i. playing the advertisement on at least one output module configured on the IoT device.

[0039] In another embodiment, the method for providing context-based advertisements in automatic mode, comprises the following:
a. connecting speech transmission means/ communication unit to the IoT device via a network means;
b. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
c. analyzing speech input data and identifying keywords related to advertisements by the processing unit;
d. transmitting recognized keywords and analyzed data to a central server module through the speech transmission means/ communication unit;
e. processing keywords and comparing the recognized keywords from the keywords of the pre-set data to obtain a matching advertisement in real-time;
f. selecting the advertisements based on the matching keyword from a data set of the advertisements stored in the storage module;
g. updating new advertisements and/ or new keywords in the software module;
h. transmitting the selected advertisement to the output module of the IoT device;
i. triggering playback of advertisement related to keywords through an output module;
j. playing the advertisement on at least one output module configured on the IoT device.

[0040] In yet another embodiment, the use of contextual ads on physical spaces is a smart way to reach consumers who are already in the market for specific products or services. By capturing the voices of people who are discussing relevant topics, advertisers can deliver targeted ads that are more likely to generate interest and lead to conversions. The concept of contextual ads on physical spaces represents a new frontier in advertising, where technology and real-world interactions converge to create powerful marketing opportunities.

[0041] In yet another embodiment, the smart IoT device for contextual ads on physical spaces is a sophisticated tool that leverages advanced technologies such as machine learning, natural language processing, and automatic speech recognition technology to deliver targeted advertisements to consumers in real-time. With its microphone array, processing unit, storage unit, communication unit, and audio/video modules, the system provides a powerful tool for advertisers looking to reach consumers where they are most receptive to their message.

[0042] The advantages of the present invention are discussed herein:
• The use of IoT devices and a central server module provides a flexible and adaptable solution for businesses of all sizes and types, allowing them to easily update their advertisements and keywords to reflect changing business needs and basis the local language, relevancy and location of the device.
• The configuration allows multiple permutation and combinations for playing the advertisement, including but not limited to, the time of the day, day of the week, month, language of keywords, location of deployment, medium of deployment, profile of the requestor (male, female, child), single or group and so on.
• The use of microphone arrays and real-time targeting provides a more cost-effective advertising solution, allowing businesses to target advertisements to users who are most likely to be interested in their products or services.
• The system aids in providing improved results in the field of physical spaces, requiring large concentration of people and a need for real-time and context-based advertising, including public places, malls, shops, retail outlets, supermarkets, and the like.
• Additionally, the system can be configured to start relaying a message repeatedly basis the configuration or backend command / instruction e.g. in case of an emergency
• Finally, the system can be configured to play an advertisement or a message, basis explicit request of the user as in a verbal command.

[0043] While this invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
, Claims:WE CLAIM:
1. A system for providing context-based advertisements in physical spaces, comprising:
• a plurality of Internet of Things (IoT) devices configured in a plurality of physical spaces;
• a microphone array installed in the IoT devices to capture speech inputs of people in vicinity;
• a processing unit wiredly/wirelessly connected to the microphone array to receive speech inputs;
• a storage unit wiredly/wirelessly connected to the IoT devices to store a plurality of keywords related to advertisements, and pre-set video data based on keywords; and
• an output module wiredly/wirelessly connected to the processing unit;
wherein,
the processing unit analyzes and identifies a plurality of keywords received from the microphone array, so as to compare identified keywords with pre-set video data and/ or keywords fed into the software module to trigger playback of advertisement related to keywords through an output module.
2. The system as claimed in claim 1, wherein the system is configured to be operated in any one of the two mode: automatic mode; or manual mode.
3. The system as claimed in claim 1, wherein the IoT devices come with a built-in speaker and video output through which any HDMI screen/display can be connected to the output module.
4. The system for providing context-based advertisements in physical spaces through manual mode, comprising:
i. the IoT devices configured in a plurality of physical spaces;
ii. the microphone array installed in the IoT devices to capture audio data/ speech inputs of people in vicinity;
iii. the storage unit wiredly/ wirelessly connected to the IoT devices stores a plurality of keywords related to advertisements and pre-set of video data;
iv. an automatic search recognition (ASR) module configured to convert recorded audio data/ speech input to text data;
v. the processing unit wiredly/ wirelessly connected to the ASR module, comprising:
a. a natural language processing (NLP) module to analyze text data received from the ASR module, so as to identify keywords related to advertisements;
b. a machine learning (ML) module for comparing identified keywords with the pre-set video data of the software module, so as to trigger playback of advertisement related to identified keywords.
vi. the output module wiredly/ wirelessly receives playback of advertisement from the ML module of the processing unit and trigger advertisement through audio and/ or video modalities.
5. The system for providing context-based advertisements in physical spaces through automatic mode, comprising:
i. the IoT devices configured in a plurality of physical spaces;
ii. the microphone array installed in the IoT devices to capture audio data/ speech inputs of people in vicinity;
iii. the storage unit wiredly/ wirelessly connected to the IoT devices stores a plurality of keywords related to advertisements and pre-set of video data;
iv. a processing unit to analyze and identify keywords from speech inputs received from the microphone array;
v. a speech transmission means configured to wirelessly transmit identified keywords from the processing unit to a central server module;
vi. the central server module configured to process recognized keywords received from the processing unit and compare recognized keywords from the keywords of the pre-set data to obtain a matching advertisement in real-time;
vii. the output module wiredly/ wirelessly receives playback of advertisement from the central server module and trigger advertisement through audio and/ or video modalities.

6. The system as claimed in claim 1, wherein the physical space is selected from but not limited to public places, malls, shops, retail outlets, supermarkets etc.
7. A method of providing context-based advertisements in physical spaces, comprising:
a. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
b. transmitting speech input captured by the microphone array to the processing unit of the IoT device;
c. analyzing speech inputs and identifying keywords related to advertisements by the processing unit;
d. triggering playback of advertisement related to keywords through an output module;
e. playing the advertisement on at least one output module configured on the IoT device.

8. The method for providing context-based advertisements in manual mode, comprising:
a. pre-feeding keywords and media files related to advertisements at the storage module through edge computing;
b. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
c. transmitting speech input from the microphone array to an automatic search recognition module (ASR);
d. converting the recorded speech input/ audio data into text data via the ASR module;
e. transmitting text data to the processing unit configured with a natural language processing (NLP) module and a machine learning (ML) module;
f. analyzing text data through the NLP module to identify keywords related to advertisements;
g. analyzing keywords through the ML module by comparing identified keywords from the keywords of the pre-set video data fed into the storage module to trigger playback of relevant advertisement;
h. triggering playback of advertisement related to keywords through an output module;
i. playing the advertisement on at least one output module configured on the IoT device.

9. The method for providing context-based advertisements in automatic mode, comprising:
a. connecting speech transmission means/ communication unit to the IoT device via a network means;
b. receiving speech inputs from a plurality of users in proximity via a microphone array placed on a plurality of IoT devices placed in physical space;
c. analyzing speech input data and identifying keywords related to advertisements by the processing unit;
d. transmitting recognized keywords and analyzed data to a central server module through the speech transmission means/ communication unit;
e. processing keywords and comparing the recognized keywords from the keywords of the pre-set data to obtain a matching advertisement in real-time;
f. selecting the advertisements based on the matching keyword from a data set of the advertisements stored in the storage module;
g. updating new advertisements and/ or new keywords in the software module;
h. transmitting the selected advertisement to the output module of the IoT device;
i. triggering playback of advertisement related to keywords through an output module;

j. playing the advertisement on at least one output module configured on the IoT device.